Method and system for retrieving statements of information sources and associating a factuality assessment to the statements

• US 8,086,557 B2
• Filed: 04/22/2008
• Issued: 12/27/2011
• Est. Priority Date: 04/22/2008
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Ait-Mokhtar, Salah, Rebotier, Aude, Sandor, Agnes
• Primary Examiner(s): FERNANDEZ RIVAS, OMAR F
• Application Number:
  US12/107,209
• Publication Number:
  US 20090265304A1
• Time in Patent Office: 1,344 Days
• Field of Search: None
• US Class Current: 706/62
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A system and method for providing a factuality assessment of a retrieved information source'"'"'s statement are disclosed. The method includes receiving a user'"'"'s query which identifies an information source whose statements are to be retrieved, retrieving documents which refer to the information source, mapping statements in the retrieved documents to their authors, identifying as information source statements, the mapped statements that are mapped to an author which is compatible with the information source, and for at least one of the information source'"'"'s statements, assessing a factuality of the information source'"'"'s statement according to the information source.

Claims

1. A computer implemented method for providing a factuality assessment of a retrieved information source'"'"'s statement comprising:

with a processor;

receiving a user'"'"'s query which identifies an information source whose statements are to be retrieved;

retrieving documents which refer to the information source;

mapping statements in the retrieved documents to their authors;

identifying as information source statements, the mapped statements that are mapped to an author which is compatible with the information source;

for at least one of the information source'"'"'s statements, assessing a factuality of the information source'"'"'s statement according to the information source.

2. The method of claim 1, wherein the factuality assessment is based on the form of the statement.

3. The method of claim 1, further comprising:

marking the information source'"'"'s statement based on its assessed factuality.

4. The method of claim 1, wherein the factuality is selected from a plurality of factuality modalities.

5. The method of claim 3, wherein the factuality modalities comprise factual, counter-factual, and possible.

6. The method of claim 1, wherein the mapping includes determining whether a retrieved document is structured or semi-structured and, if so, applying shallow natural language processing to map a statement of the retrieved document to its author.

7. The method of claim 5, wherein when a retrieved document determined not to be structured or semi-structured, the method includes applying more robust natural language processing to map a statement of the retrieved document to its author.

8. The method of claim 1, wherein the method further includes identifying whether an expression for information transfer is present in a retrieved document and for the identified expression, processing a sentence in which the expression occurs to identify a candidate statement in the sentence.

9. The method of claim 7, comprising accessing a lexicon in which text elements which are expressions of information transfer are indexed as such for identifying whether an expression for information transfer is present in a retrieved document.

10. The method of claim 1, further comprising presenting an identified information source'"'"'s statement to a user together with an indication of its factuality.

11. The method of claim 1, wherein the assessing of the factuality of the information source'"'"'s statement comprises identifying a form of at least one predicate in the statement and determining the factuality of the statement based on the form of the at least one predicate.

12. The method of claim 10, wherein when the statement includes an embedded predicate, determining a type of relationship between the embedded predicate and an embedding predicate which embeds it and assigning a factuality to the embedded predicate based on an assigned factuality of the embedding predicate and the type of relationship.

13. The method of claim 11, wherein when a sole or embedding predicate is a verb, its factuality is a function of the tense of the verb.

14. The method of claim 1, wherein the information source is a named entity selected from person names and organization names.

15. A computer program product comprising a non-transitory recording medium which encodes instructions which, when executed by a computer, perform the method of claim 1.

16. A system for providing a factuality assessment of a retrieved information source'"'"'s statement comprising memory which stores instructions for performing the method of claim 1 and a processor in communication with the memory, for executing the instructions.

17. A system for providing a factuality assessment of a retrieved information source'"'"'s statement comprising:

memory which stores as software instructions;

a query formulator for receiving a user'"'"'s query which identifies an information source whose statements are to be retrieved and generates a query for retrieving documents from an associated source of documents which refer to the information source;

a mapping component for mapping statements in the retrieved documents to their authors and identifying as an information source'"'"'s statement, a statement that is mapped to an author which is compatible with the information source;

a factuality determiner, which determines a factuality of the information source'"'"'s statements, based on the content of the statement; and

a processing component in communication with the memory, which executes the instructions.

18. The system of claim 17, wherein the factuality determiner marks the information source'"'"'s statement based on its determined factuality.

19. The system of claim 17, wherein the mapping includes determining whether a retrieved document is structured or semi-structured and, if so, applying shallow natural language processing to map a statement of the retrieved document to its author.

20. The system of claim 17, further comprising a parser which performs robust natural language processing for mapping a statement of a retrieved unstructured document to its author.

21. The system of claim 17, further comprising a lexicon accessible by the mapping component, in which text elements which are expressions of information transfer are indexed as such for identifying whether an expression for information transfer is present in a retrieved document.

22. The system of claim 17, further comprising a presenter for presenting an identified information source'"'"'s statement to a user together with an indication of its factuality.